The importance of good practices and false hits for QSAR-driven virtual screening real application: a SARS-CoV-2 main protease (Mpro) case study

Computer-Aided Drug Design (CADD) approaches, such as those employing quantitative structure-activity relationship (QSAR) methods, are known for their ability to uncover novel data from large databases. These approaches can help alleviate the lack of biological and chemical data, but some predictions do not generate sufficient positive information be useful screenings. QSAR models often employed explain chemicals design new based on predictions. In this review, we discuss importance set size with a focus false hits approaches. We assess challenges reliability an initial in silico strategy virtual screening bioactive molecules. Lastly, present case study reporting combination approach hologram-based (HQSAR) random forest-based (RF-QSAR), 3D structures 25 synthetic SARS-CoV-2 M pro inhibitors, virtually screen compounds potential inhibitors enzyme activity. study, optimal were selected predict database Brazilian Compound Library (BraCoLi). Twenty-four then assessed against at 10 µM. At time (March 2021), availability varied different that reported definitely affected our work. Since no obtained, size, parameters employed, external validations, well applicability domain (AD) could considered regarding contribution, aiming enhance discovery